Update README.md
Browse files
README.md
CHANGED
@@ -2,26 +2,20 @@
|
|
2 |
license: apache-2.0
|
3 |
---
|
4 |
|
5 |
-
|
6 |
-
2. Purpose
|
7 |
-
3. Installation Instructions
|
8 |
-
4. Usage Instructions
|
9 |
-
5. Model Architecture
|
10 |
-
6. Training Details
|
11 |
-
7. Evaluation
|
12 |
-
8. Examples
|
13 |
-
9. Contributing
|
14 |
-
10. License
|
15 |
|
16 |
-
|
|
|
|
|
17 |
|
18 |
-
|
19 |
-
This project provides a Convolutional Neural Network (CNN) model for classifying images as either 'real' or 'fake'. The model is based on the ResNet50 architecture and has been fine-tuned for binary classification tasks.
|
20 |
|
21 |
-
|
22 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
23 |
|
24 |
-
## Installation
|
25 |
-
Ensure you have the following dependencies installed:
|
26 |
-
```bash
|
27 |
-
pip install tensorflow numpy opencv-python scikit-learn
|
|
|
2 |
license: apache-2.0
|
3 |
---
|
4 |
|
5 |
+
Real vs AI-Generated Image Classification
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
6 |
|
7 |
+
This project provides a Convolutional Neural Network (CNN) model for classifying images as either 'real' or 'fake'.
|
8 |
+
CNN is a type of deep learning model specifically designed to process and analyze visual data by applying convolutional layers that automatically detect patterns and features in images.
|
9 |
+
Our CNN model is based on 2,800 real images and AI-generated images, which are divided equally.
|
10 |
|
11 |
+
Our goal is to accurately classify the source of the image with at least 85% accuracy and achieve at least 80% in the Recall test.
|
|
|
12 |
|
13 |
+
5. Installation Instructions
|
14 |
+
6. Usage Instructions
|
15 |
+
7. Model Architecture
|
16 |
+
8. Training Details
|
17 |
+
9. Evaluation
|
18 |
+
10. Examples
|
19 |
+
11. Contributing
|
20 |
+
12. License
|
21 |
|
|
|
|
|
|
|
|